© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10128
    Prev
    Next
    INDEX
    Explanations

    place names and their parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     by
    -2.23
     on
    -1.99
     so
    -1.84
     you
    -1.77
     all
    -1.77
     at
    -1.65
     as
    -1.62
     From
    -1.59
     a
    -1.58
     in
    -1.56
    POSITIVE LOGITS
     refroid
    1.73
    cisive
    1.66
    sistence
    1.56
     olabilir
    1.48
    
    1.47
     couvrir
    1.46
     représentent
    1.45
     comprennent
    1.41
     adhesivo
    1.40
     compléter
    1.39
    Activations Density 0.103%

    No Known Activations